Cooperative filtering, identification, and mapping for spatially distributed systems using mobile sensor networks

Abstract

Since the performance of parameter and state estimation depends on the trajectories of mobile sensors, we further design the online trajectory planning algorithms based on a novel geometric reinforcement learning (GRL) algorithm, so that the sensors can use the local real-time information to guide them to move along knowledge-rich paths that can increase the performance of the parameter identification and map construction. The basic idea of GRL is to divide the whole area into a series of lattice to employ a specific reward matrix, which contains the information of the length of the path and the mapping error. Thus, the proposed GRL can balance the performance of the field reconstruction and the efficiency of the path. By updating the reward matrix, the real-time path planning problem can be converted to the shortest path problem in a weighted graph, which can be solved efficiently using dynamic programming.